Skip to main content
Glama
RapidMiner / Altair AI Studio MCP

RapidMiner / Altair AI Studio MCP

rm_click

Click UI components by id, text, tooltip or class, or click screen coordinates. Supports right-click for context menus and double-click actions in AI Studio.

Instructions

Click a component (id or text/name/tooltip/class query) or a point (x,y). Buttons are pressed via their action; other components get real mouse events. Supports right-click (context menus) and double-click.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "rm_click"
  }
}

Input Schema

NameRequiredDescriptionDefault
xNoX in window coordinates (pixels of an unscaled rm_screenshot)
yNoY in window coordinates
idNoComponent id from rm_ui_tree / rm_ui_find
nameNoMatch Swing component name
textNoMatch visible text / label (substring, case-insensitive)
classNoMatch Java class name, e.g. JButton, JTree
exactNoExact (not substring) text match
indexNoWhich match to use when several match (0-based)
scaleNoIf x/y come from a scaled screenshot, pass that scale
buttonNo
clicksNo2 = double-click
windowNoWindow id from rm_windows (default: active window)
tooltipNoMatch tooltip text
wait_msNo
offset_xNoPoint inside the component (default: center)
offset_yNo
modifiersNoe.g. 'ctrl', 'shift', 'ctrl+shift'
syntheticNoForce mouse events even for buttons

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and does disclose real behavior beyond the schema: buttons fire through their action rather than synthesized events, non-button components receive genuine mouse events, and right-click/context-menu and double-click are explicitly supported. It still omits what happens on zero or multiple matches, whether wait_ms blocks, and what the call returns, which keeps it short of a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, front-loaded with the core targeting modes and followed by the behavioral caveat and capability list. Dense and waste-free, though the stacked parentheticals make the first sentence slightly harder to parse than it needs to be.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 18-parameter tool with no annotations and no output schema, the description covers the targeting model and event semantics but is silent on the wait/polling behavior, match-resolution failure modes, return value, and window-activation side effects. Adequate to call it correctly in the common case, incomplete for edge cases.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 83%, so the schema already explains nearly every parameter, making 3 the baseline. The description usefully groups the parameters into two modes (component query vs. x,y point) and hints at the synthetic-vs-action distinction, but adds no syntax, format, or default details beyond what the schema states.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (click) plus the two targeting modes it accepts — component queries via id/text/name/tooltip/class, or a raw x,y point — so an agent immediately knows this is the pointer-activation tool. It does not name rm_drag or rm_key as alternatives, so sibling differentiation is left implicit, but the action is unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The clause 'Buttons are pressed via their action; other components get real mouse events' implies that semantic action buttons are handled specially and that raw events hit everything else, which is useful selection guidance. However, there is no explicit when-to-use/when-not guidance, no advice on preferring a component query over coordinates, and no mention of when to reach for rm_drag, rm_key, or rm_scroll instead.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.